Triple
T22992687
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Louis I, Prince of Condé |
E572093
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Louis |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Louis | Statement: [Louis I, Prince of Condé, givenName, Louis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Louis Context triple: [Louis I, Prince of Condé, givenName, Louis]
-
A.
Louis
Louis is the friendly, trumpet-playing alligator who dreams of becoming a jazz musician in Disney's animated film "The Princess and the Frog."
-
B.
Louis
Louis is a member of the British royal family, the youngest child of William, Prince of Wales, and Catherine, Princess of Wales.
-
C.
Louis
Louis is the given name of Louis Althusser, a prominent 20th-century French Marxist philosopher known for his structuralist interpretation of Marxism.
-
D.
Louis
Louis was the given name of Louis II, Duke of Bavaria, a medieval German nobleman and regional ruler.
-
E.
Louis
chosen
Louis was a French nobleman of the Bourbon-Condé line who held the title of comte de Clermont and was active in 18th-century military and court life.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e245b535808190adef8a9df3c584db |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182f017a88190b02d0649a3af5d99 |
completed | April 29, 2026, 4:02 a.m. |
Created at: April 17, 2026, 3:50 p.m.